When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes

Author(s)
Tucker, Mycal; Eisape, Tiwalayo; Qian, Peng; Levy, Roger; Shah, Julie
Thumbnail
DownloadPublished version (708.6Kb)
Publisher Policy
Terms of use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Metadata
Show full item record
Date issued
2022
URI
https://hdl.handle.net/1721.1/150010
Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Journal
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Publisher
Association for Computational Linguistics (ACL)
Citation
Tucker, Mycal, Eisape, Tiwalayo, Qian, Peng, Levy, Roger and Shah, Julie. 2022. "When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes." Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Version: Final published version
Collections